Data-Driven Model-Based Fault Diagnosis in a Wind Turbine With Actuator Faults
Bibliographic record
Abstract
Wind turbines are renewable energy conversion devices that are being deployed in greater numbers. However, today’s wind turbines are still expensive to operate, and maintain. The reduction of operational and maintenance costs has become a key driver for applying low-cost, condition monitoring and diagnosis systems in wind turbines. Accurate and timely detection, isolation and diagnosis of faults in a wind turbine allow satisfactory accommodation of the faults and, in turn, enhancement of the reliability, availability and productivity of wind turbines. The so–called model-based Fault Detection and Diagnosis (FDD) approaches utilize system model to carry out FDD in real-time. However, wind turbine systems are driven by wind as a stochastic aerodynamic input, and essentially exhibit highly nonlinear dynamics. Accurate modeling of such systems to be suitable for use in FDD applications is a rather difficult task. Therefore, this paper presents a data-driven modeling approach based on artificial intelligence (AI) methods which have excellent capability in describing complex and uncertain systems. In particular, two data-driven dynamic models of wind turbine are developed based on Fuzzy Modeling and Identification (FMI) and Artificial Neural Network (ANN) methods. The developed models represent the normal operating performance of the wind turbine over a full range of operating conditions. Consequently, a model-based FDD scheme is developed and implemented based on each of the individual models. Finally, the FDD performance is evaluated and compared through a series of simulations on a well-known large offshore wind turbine benchmark in the presence of wind turbulences, measurement noises, and different realistic fault scenarios in the generator/converter torque actuator.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".